1 / 27

Challenges of Technology Scaling in ECE/CS

Explore the challenges faced in technology scaling, such as transistor variability, degradation, power density, and leakage power. Discover solutions and the future of computer architecture.

dleslie
Download Presentation

Challenges of Technology Scaling in ECE/CS

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Technology ChallengesECE/CS 752 Fall 2017 Prof. Mikko H. Lipasti University of Wisconsin-Madison

  2. Readings • Read on your own: • Shekhar Borkar, Designing Reliable Systems from Unreliable Components: The Challenges of Transistor Variability and Degradation, IEEE Micro 2005, November/December 2005 (Vol. 25, No. 6) pp. 10-16. • 2015 ITRS Roadmap -- Executive Summary. Read sections 1, 5, 6, 8, 9, and skim the rest. • Review by Wed 9/13/2017: • Jacobson, H, et al., “Stretching the limits of clock-gating efficiency in server-class processors,” in Proceedings of HPCA-11, 2005.

  3. Moore’s Law (1965) G. E. Moore, “Cramming More Components onto Integrated Circuits,” Electronics Vol. 38, No. 8 (Apr. 19, 1965) pp. 114-117.

  4. Dennard Scaling (1974) R. Dennard et. al, "Design of ion-implanted MOSFET's with very small physical dimensions” IEEE Journal of Solid State Circuits. SC–9 (5)

  5. End of Dennard Scaling • Everything was great! No tradeoffs at all… • Density doubling every two years (Moore’s law) • Feature size • Device density • Device switching speed improves 30-40%/generation • Supply & threshold voltages decrease (Vdd, Vth) • This ended around 2000 • Now, feature size, device density scaling continues • Roadmap well below 10nm generation • Switching speed improves ~20%/generation or less • Voltage scaling has tapered off • SRAM cell stability becomes an issue at ~0.7V Vdd • Still cheaper (or denser) but power-limited

  6. Summary of Challenges From “21st Century Computer Architecture: A community white paper,” Computing Research Assocation (CRA), 2012

  7. Solutions? • New markets will drive demand and need for innovation • Datacenters • IoT • Mobile • Incremental (one-time) improvements • Copper, high-K dielectric, FinFETs, … • Packaging: 2.1D, 2.5D, 3D • Beyond CMOS • Carbon nanotubes, spin FET, • “More than Moore” • Analog, RF, accelerators, non-Von Neumann, …

  8. Power Density [Hu et al, MICRO ’03 tutorial] • Power density increasing exponentially • Power delivery, packaging, thermal implications • Thermal effects on leakage, delay, reliability, etc.

  9. Dynamic Power • Aka AC power, switching power • Static CMOS: current flows when transistors turn on/off • Combinational logic evaluates • Sequential logic (flip-flop, latch) captures new value (clock edge) • Terms • C: capacitance of circuit (wire length, no. & size of transistors) • V: supply voltage • A: activity factor • f: frequency • Moore’s Law: which terms increase, which decrease? • Voltage scaling has been saving our bacon!

  10. Reducing Dynamic Power • Reduce capacitance • Simpler, smaller design • Reduced IPC • Reduce activity • Smarter design • Reduced IPC • Reduce frequency • Often in conjunction with reduced voltage • Reduce voltage • Biggest hammer due to quadratic effect, widely employed • Can be static (binning/sorting of parts), and/or • Dynamic (power modes) • E.g. Transmeta Long Run, AMD PowerNow, Intel Speedstep

  11. Frequency/Voltage relationship • Lower voltage implies lower frequency • Lower Vth increases delay to sense/latch 0/1 • Conversely, higher voltage enables higher frequency • Overclocking • Sorting/binning and setting various Vdd & Vth • Characterize device, circuit, chip under varying stress conditions • Black art – very empirical & closely guarded trade secret • Implications on reliability • Safety margins, product lifetime • This is why overclocking is possible

  12. Frequency/Voltage Scaling • Voltage/frequency scaling rule of thumb: • +/- 1% performance buys -/+ 3% power (3:1 rule) • Hence, any power-saving technique that saves less than 3x power over performance loss is uninteresting • Example 1: • New technique saves 12% power • However, performance degrades 5% • Useless, since 12 < 3 x 5 • Instead, reduce f by 5% (also V), and get 15% power savings • Example 2: • New technique saves 5% power • Performance degrades 1% • Useful, since 5 > 3 x 1 • Does this rule always hold?

  13. Leakage Power (Static/DC) Source • Transistors aren’t perfect on/off switches • Even in static CMOS, transistors leak • Channel (source/drain) leakage • Gate leakage through insulator • High-K dielectric replacing SiO2 helps • Leakage compounded by • Low threshold voltage • Low Vth => fast switching, more leakage • High Vth => slow switching, less leakage • Higher temperature • Temperature increases with power • Power increases with C, V2, A, f • Rough approximation: leakage proportional to area • Transistors aren’t free, unless they’re turned off • Could be a huge problem in future technologies • Estimates are 40%-50% of total power Gate Drain

  14. Power Power vs. Energy Energy Time • Energy: integral of power (area under the curve) • Energy & power driven by different design constraints • Power issues: • Power delivery (supply current @ right voltage) • Thermal (don’t fry the chip or make user uncomfortable) • Reliability effects (chip lifetime) • Energy issues: • Limited energy capacity (battery) • Efficiency (work per unit energy) • Different usage models drive tradeoffs

  15. Power vs. Energy • With constant time base, two are “equivalent” • 10% reduction in power => 10% reduction in energy • Once time changes, must treat as separate metrics • E.g. reduce frequency to save power => reduce performance => increase time to completion => consume more energy (perhaps) • Metric: energy-delay product per unit of work • Tries to capture both effects, accounts for quadratic savings from DVS • Others advocate energy-delay2 (accounts for cubic effect) • Best to consider all • Plot performance (time), energy, ed, ed2

  16. Usage Models • Thermally limited => dynamic power dominates • Max power (“power virus” contest at Intel) • Must deliver adequate power (or live within budget) • Must remove heat • From chip, from case, room, building, pocket • Chip hot spots cause problems • Efficiency => dynamic & static power matter • E.g. energy per DVD frame • Analogy: cell-phone “talk time” • Longevity => static power dominates • Minimum power while still “awake” • Cellphone “standby” time • Laptop still responds quickly • Not suspend/hibernate • “Power state” management very important • Speedstep, PowerNow, LongRun Worst Case Average Case Best Case

  17. Circuit-Level Techniques • Multiple voltages • Realize non-critical circuits with slower transistors • Voltage islands: Vdd and Vth are lower • Problem: supplying multiple Vdd • MTCMOS: only Vth is lower • Multiple frequencies • Globally Asynchronous Locally Synchronous (GALS) • Exploiting safety margins • Average case vs. worst case design • Razor latch [UMichigan]: • Sample latch input twice, then compare, recover • Body biasing • Reduce leakage by adapting Vth

  18. Architectural Techniques • Multicore chips (later) • Clock gating (dynamic power) • 70% of dynamic power in IBM Power5 [Jacobson et al., HPCA 04] • Inhibit clock for • Functional block • Pipeline stage • Pipeline register (sub-stage) • Widely used in real designs today • Control overhead, timing complexity (violates fully synchronous design rules) • Power gating (leakage power) • Sleep transistors cut off Vdd or ground path • Apply to FU, cache subarray, even entire core in CMP

  19. Architectural Techniques • Cache reconfiguration (leakage power) • Not all applications or phases require full L1 cache capacity • Power gate portions of cache memory • State-preservation • Flush/refill (non-state preserving) [Powell et al., ISLPED 00] • Drowsy cache (state preserving) [Flautner, Kim et al., ISCA 02] • Complicates a critical path (L1 cache access) • Does not apply to lower level caches • High Vth (slower) transistors already prevent leakage

  20. Architectural Techniques • Heterogeneous cores [Kumar et al., MICRO-36] • Prior-generation simple core consumes small fraction of die area • Use simple core to run low-ILP workloads • E.g. ARM’s big.LITTLE • Configurable cores: dynamically vary ILP vs. power • Filter caches (dynamic power) • Many references are required for correctness but result in misses • External snoops [Jetty, HPCA ‘01] • Load/store alias checks [Sethumadhavan et al., MICRO ‘03] • Filter caches summarize cache contents (e.g. Bloom filter) • Much smaller filter cache lookup avoids lookup in large/power-hungry structure • And many others…check proceedings of • ISLPED, MICRO, ISCA, HPCA, ASPLOS, PACT

  21. Variability • Shrinking device dimensions lead to sensitivity to minor processing variations “No two transistors are the same” • Die-to-die variations • Across multiple die on same wafer, across wafers • Within-die variations • Systematic and random • E.g. line edge roughness due to sub-wavelength lithography or dopant variations (~10 molecules) • Dynamic variations • E.g. temperature-induced variability (hot spots)

  22. 2D Packaging [M. Maxfield, “2D vs. 2.5D vs. 3D ICs 101,” EE Times, April 2012] Conventional packaging approaches Board level System on Chip

  23. 2D Packaging [M. Maxfield, “2D vs. 2.5D vs. 3D ICs 101,” EE Times, April 2012] Move toward System in Package (SIP) • PCB, ceramic, semiconductor substrates

  24. 2.5D Packaging [M. Maxfield, “2D vs. 2.5D vs. 3D ICs 101,” EE Times, April 2012] 2.5D uses silicon interposer, through-silicon vias (TSV) 2D Packaging 2.5D Packaging

  25. 3D Packaging [M. Maxfield, “2D vs. 2.5D vs. 3D ICs 101,” EE Times, April 2012] 3D uses through-silicon vias (TSV) and/or interposer 3D Homogeneous 3D Heterogeneous

  26. Packaging Discussion • Heterogeneous integration • RF, analog (PHY), FG/PCM/ReRAM, photonics • Cost • Silicon yield • Bandwidth, esp. interposer • Thermals • It’s real! • DRAM: HMC, HBM • FPGAs • GPUs: AMD, NVIDIA • CPUs: AMD Zen, EPYC

  27. Summary • Technology scaling, Moore vs. Dennard • Power: dynamic, static • CMOS scaling trends • Power vs. Energy • Dynamic power vs. leakage power • Usage Models: thermal, efficiency, longevity • Circuit Techniques • Architectural Techniques • Variability • Packaging

More Related